Benchmark Almanac

The Illusion of AI Safety

Not in model cards

Chatbots answer 30 prompts about self-harm, eating disorders, and substance use. Researchers check replies for harmful content and invitations to continue the conversation.

Slingshot AI reran the prompts with four models and evaluated 24,000 responses across the initial and follow-up turns.

Released
October 2025
Kind
Wellbeing and sycophancy
Level
University
Scored
Graded by people
Answers
Open-ended
Tasks
All public
Measures
Propensity
Language
English
In and out
Text → Text
Interaction
Multi-turn
Items from
Written by experts
Refresh
One fixed set
Run by
Anyone
In views
Content safety
Strongest model tested
GPT-5 #71 on the capability index
Last model added
August 2025
Scores refreshed
November 21st, 2026
2
Models scored in its paper

GPT-4o leads with 43%

Best score per model from the benchmark's paper, read on November 21st, 2026. A paper’s table doesn’t add newer models. Where a model ran with several settings or harnesses, we keep its best.

  1. 1 GPT-4o Mar 2025 43%
  2. 2 GPT-5 53%

Source: The The Illusion of AI Safety paper

#ModelScoreSettingDateSource
1 GPT-4o Mar 2025 43% Mar 2025 Official leaderboard
2 GPT-5 53% Aug 2025 Official leaderboard

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

In the benchmark’s paper
0% 20% 40% 60% 80% 100% 2025 GPT-4o 0% 20% 40% 60% 80% 100% 2025 GPT-4o

Source: Official The Illusion of AI Safety leaderboard

No lab model card reports it yet

We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.

More in Safety and alignment

All 636 in Safety and alignment
  • FORTRESS In use Paired adversarial and benign national-security misuse prompts. Rubric-graded risk score on adversarial and over-refusal score on benign prompts. Claude Opus 5.5 5.78%
  • StrongREJECT In use Forbidden-prompt jailbreak benchmark with a rubric grader that scores how useful a non-refusal actually is. Inkling 98.6%
  • Gray Swan IPI Arena benchmark In use Indirect prompt-injection attacks from public red-teaming competitions replayed on tool, coding and browser agents. Attack success rate at k attempts. Gemini 4 Carbon 0%
  • Covert misbehavior (Thinking Machines) In use Agentic tasks that check whether a model misbehaves and conceals it. Scored by the rate of covert misbehavior. Inkling 2 Mini 8.30%
  • Destructive actions (Thinking Machines) In use Agentic tasks that check whether a model takes destructive actions it was not authorized to take. Scored by the rate of destructive actions. Inkling 2 Small 4.70%
  • Misbehavior (Thinking Machines) In use Agentic tasks that check whether a model fabricates results, ignores instructions or hides what it did when a task is hard. Scored by the rate of misbehavior. Inkling 2 Mini 9.80%

Data audit

7 of 8 checks pass, 1 warning. Look first at the Newest score check. The newest came 15 months ago, in August 2025, for GPT-5. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 1 warning 1 pass 3 notes
  • Pass Independent runs Scores from the benchmark’s paper (2 entries).
  • Note Models scored Only 2 models we track.
  • Warning Newest score The newest came 15 months ago, in August 2025, for GPT-5.
  • Note Frontier models None of the top 10 has a score. The strongest tested is GPT-5 (#71).
  • Note Headroom Lower is better, so there’s no ceiling to reach.
Leaderboard import 3 pass
  • Pass Importer We read the board on counterharm.com: 2 rows for models we track at the last read.
  • Pass Last read November 21st, 2026.
  • Pass Read worked The last read worked.
Consistency 1 pass 1 note
  • Note Lab claims No model has both a lab number and an independent run.
  • Pass Known issues No published audit found problems.

How we check